Multifractal computation for nuclear classification and hepatocellular carcinoma grading

Chamidu Atupelage, Hiroshi Nagahashi, Masahiro Yamaguchi, Fumikazu Kimura, Tokiya Abe, Akinori Hashiguchi, Michiie Sakamoto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Hepatocellular carcinoma (HCC) is graded mainly based on the characteristics of liver cell nuclei. This paper proposes a textural feature descriptor and a novel computational method for classifying liver cell nuclei and grading the HCC histological images. The proposed textural feature descriptor observes local and spatial characteristics of the texture patterns by using multifractal computation. The textural features are utilized for nuclear segmentation, fiber region detection, and liver cell nuclei classification. Four categories of nuclear features are computed such as texture, geometry, spatial distribution, and surrounding texture, for HCC classification. Significance of liver cell nuclei classification method is evaluated by classifying non-neoplastic and tumor tissues. Furthermore, characteristics of the liver cell nuclei were utilized for grading a set of HCC images into four classes and obtained 97.77% classification accuracy.

Original languageEnglish
Title of host publicationProceedings of the IASTED International Conference on Biomedical Engineering, BioMed 2013
Pages415-420
Number of pages6
DOIs
Publication statusPublished - 2013
Event10th IASTED International Conference on Biomedical Engineering, BioMed 2013 - Innsbruck, Austria
Duration: 2013 Feb 132013 Feb 15

Other

Other10th IASTED International Conference on Biomedical Engineering, BioMed 2013
CountryAustria
CityInnsbruck
Period13/2/1313/2/15

Fingerprint

Liver
Cells
Textures
Computational methods
Spatial distribution
Tumors
Tissue
Geometry
Fibers

Keywords

  • Cancer grading
  • Feature descriptor
  • HCC histological images
  • Multifractal computation
  • Multifractal measures

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Atupelage, C., Nagahashi, H., Yamaguchi, M., Kimura, F., Abe, T., Hashiguchi, A., & Sakamoto, M. (2013). Multifractal computation for nuclear classification and hepatocellular carcinoma grading. In Proceedings of the IASTED International Conference on Biomedical Engineering, BioMed 2013 (pp. 415-420) https://doi.org/10.2316/P.2013.791-127

Multifractal computation for nuclear classification and hepatocellular carcinoma grading. / Atupelage, Chamidu; Nagahashi, Hiroshi; Yamaguchi, Masahiro; Kimura, Fumikazu; Abe, Tokiya; Hashiguchi, Akinori; Sakamoto, Michiie.

Proceedings of the IASTED International Conference on Biomedical Engineering, BioMed 2013. 2013. p. 415-420.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Atupelage, C, Nagahashi, H, Yamaguchi, M, Kimura, F, Abe, T, Hashiguchi, A & Sakamoto, M 2013, Multifractal computation for nuclear classification and hepatocellular carcinoma grading. in Proceedings of the IASTED International Conference on Biomedical Engineering, BioMed 2013. pp. 415-420, 10th IASTED International Conference on Biomedical Engineering, BioMed 2013, Innsbruck, Austria, 13/2/13. https://doi.org/10.2316/P.2013.791-127
Atupelage C, Nagahashi H, Yamaguchi M, Kimura F, Abe T, Hashiguchi A et al. Multifractal computation for nuclear classification and hepatocellular carcinoma grading. In Proceedings of the IASTED International Conference on Biomedical Engineering, BioMed 2013. 2013. p. 415-420 https://doi.org/10.2316/P.2013.791-127
Atupelage, Chamidu ; Nagahashi, Hiroshi ; Yamaguchi, Masahiro ; Kimura, Fumikazu ; Abe, Tokiya ; Hashiguchi, Akinori ; Sakamoto, Michiie. / Multifractal computation for nuclear classification and hepatocellular carcinoma grading. Proceedings of the IASTED International Conference on Biomedical Engineering, BioMed 2013. 2013. pp. 415-420
@inproceedings{8d849df34cf246b58951cf1bb3ef2dcb,
title = "Multifractal computation for nuclear classification and hepatocellular carcinoma grading",
abstract = "Hepatocellular carcinoma (HCC) is graded mainly based on the characteristics of liver cell nuclei. This paper proposes a textural feature descriptor and a novel computational method for classifying liver cell nuclei and grading the HCC histological images. The proposed textural feature descriptor observes local and spatial characteristics of the texture patterns by using multifractal computation. The textural features are utilized for nuclear segmentation, fiber region detection, and liver cell nuclei classification. Four categories of nuclear features are computed such as texture, geometry, spatial distribution, and surrounding texture, for HCC classification. Significance of liver cell nuclei classification method is evaluated by classifying non-neoplastic and tumor tissues. Furthermore, characteristics of the liver cell nuclei were utilized for grading a set of HCC images into four classes and obtained 97.77{\%} classification accuracy.",
keywords = "Cancer grading, Feature descriptor, HCC histological images, Multifractal computation, Multifractal measures",
author = "Chamidu Atupelage and Hiroshi Nagahashi and Masahiro Yamaguchi and Fumikazu Kimura and Tokiya Abe and Akinori Hashiguchi and Michiie Sakamoto",
year = "2013",
doi = "10.2316/P.2013.791-127",
language = "English",
isbn = "9780889869530",
pages = "415--420",
booktitle = "Proceedings of the IASTED International Conference on Biomedical Engineering, BioMed 2013",

}

TY - GEN

T1 - Multifractal computation for nuclear classification and hepatocellular carcinoma grading

AU - Atupelage, Chamidu

AU - Nagahashi, Hiroshi

AU - Yamaguchi, Masahiro

AU - Kimura, Fumikazu

AU - Abe, Tokiya

AU - Hashiguchi, Akinori

AU - Sakamoto, Michiie

PY - 2013

Y1 - 2013

N2 - Hepatocellular carcinoma (HCC) is graded mainly based on the characteristics of liver cell nuclei. This paper proposes a textural feature descriptor and a novel computational method for classifying liver cell nuclei and grading the HCC histological images. The proposed textural feature descriptor observes local and spatial characteristics of the texture patterns by using multifractal computation. The textural features are utilized for nuclear segmentation, fiber region detection, and liver cell nuclei classification. Four categories of nuclear features are computed such as texture, geometry, spatial distribution, and surrounding texture, for HCC classification. Significance of liver cell nuclei classification method is evaluated by classifying non-neoplastic and tumor tissues. Furthermore, characteristics of the liver cell nuclei were utilized for grading a set of HCC images into four classes and obtained 97.77% classification accuracy.

AB - Hepatocellular carcinoma (HCC) is graded mainly based on the characteristics of liver cell nuclei. This paper proposes a textural feature descriptor and a novel computational method for classifying liver cell nuclei and grading the HCC histological images. The proposed textural feature descriptor observes local and spatial characteristics of the texture patterns by using multifractal computation. The textural features are utilized for nuclear segmentation, fiber region detection, and liver cell nuclei classification. Four categories of nuclear features are computed such as texture, geometry, spatial distribution, and surrounding texture, for HCC classification. Significance of liver cell nuclei classification method is evaluated by classifying non-neoplastic and tumor tissues. Furthermore, characteristics of the liver cell nuclei were utilized for grading a set of HCC images into four classes and obtained 97.77% classification accuracy.

KW - Cancer grading

KW - Feature descriptor

KW - HCC histological images

KW - Multifractal computation

KW - Multifractal measures

UR - http://www.scopus.com/inward/record.url?scp=84883879051&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883879051&partnerID=8YFLogxK

U2 - 10.2316/P.2013.791-127

DO - 10.2316/P.2013.791-127

M3 - Conference contribution

SN - 9780889869530

SP - 415

EP - 420

BT - Proceedings of the IASTED International Conference on Biomedical Engineering, BioMed 2013

ER -